Skip to main content
Have a personal or library account? Click to login
Research on Capsule Network Based on Attention Mechanism Cover
By: Yan Jiao,  Li Zhao and  Hexin Xu  
Open Access
|Feb 2022

Figures & Tables

Figure 1.

The original capsule network

Figure 2.

CBAM Module

Figure 3.

Channel Attention Module

Figure 4.

Spatial Atttion Module

Figure 5.

Capsule network based on attention mechanism

j_ijanmc-2021-011_utab_001

ProcedureRouting algorithm
1:procedure ROUTING ( u ^ i j , i , l )
2:    for all capsule i in layer l and capsule j in layer (l + 1):bij ←0
3:    for r iterations do
4:        for all capsule i in layer l : ci ← softmax (bi )
5:        for all capsule j in layer (l +1) : sj i C i j u ^ i | j
6:        for all capsule j in layer (l +1) : vj ← squash (sj )
7:        for all capsule i in layer l and capsule j in layer (l + l)
8: return vj

NETWORK MODEL AND PARAMETERS

LayerParameters
Conv inputChannel:1; outPutChannel:256 kernel size= 9; stride=1
CBAM Channel:256
PrimaryCaps InputChannel:256;OutputCaps:32*6*6output_dim:8;kernel_size:9,stride:2
MgitCaps Inputeaps:32*6*6;out_put_caps:10

NETWORK MODEL ACCURACY

Net Work NameRouting NumberCBAM ModuleMax AccuracyFirst time
CapsNetl 1False99.70999908%133
CapsNetl_CBAM 1True99.66999817%100
CapsNet2 2False99.65000153%111
CapsNet2_CBAM 2True99.61000061%42
CapsNet3 3False99.69000244%131
CapsNet3_CBAM 3True99.62002324%82
CapsNet4 4False99.59999847%141
CapsNet4_CBAM 4True99.55999756%86
CapsNet5 5False99.65000153%125
Language: English
Page range: 1 - 8
Published on: Feb 21, 2022
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2022 Yan Jiao, Li Zhao, Hexin Xu, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution 4.0 License.